FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search

Designing accurate and efficient ConvNets for mobile devices is challenging because the design space is combinatorially large. Due to this, previous neural architecture search (NAS) methods are computationally expensive. ConvNet architecture optimality depends on factors such as input resolution and...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2019-05
Hauptverfasser:	Wu, Bichen, Dai, Xiaoliang, Zhang, Peizhao, Wang, Yanghan, Sun, Fei, Wu, Yiming, Tian, Yuandong, Vajda, Peter, Jia, Yangqing, Keutzer, Kurt
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Electronic devices Frames per second Optimization Searching Smartphones State of the art
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!